Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to software libraries and their components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otp
    -0.16
     vig
    -0.15
    ollapsed
    -0.14
    ames
    -0.14
     Gil
    -0.14
     Poh
    -0.14
    endale
    -0.14
    Ïĥο
    -0.14
    lad
    -0.13
    edii
    -0.13
    POSITIVE LOGITS
    ansk
    0.17
    ake
    0.16
    LOPT
    0.15
    .Options
    0.14
    kinson
    0.14
    achen
    0.14
    bart
    0.14
    íĮ¨
    0.13
    appa
    0.13
    chang
    0.13
    Act Density 0.252%

    No Known Activations